Robust MMSE-FW-LA ASR S
نویسنده
چکیده
In this paper, a novel feature weight (FW) algorithm for robust automatic speech recognition (ASR) is proposed. In this algorithm every feature will be weighted according to their credible probability, especially, the weight factors are formulated and obtained from the gain coefficients generated as by-products of speech enhancement based on minimum mean square error (MMSE) estimation. Moreover a new robust ASR scheme is presented. In this scheme the MMSE-based speech enhancement, the FW algorithm and the Log-Add (LA) model compensation will be integrated together. Experimental evaluations show that this MMSE-FW-LA scheme can achieve significant improvement in recognition across a wide range of signal-to-noise ratios (SNR), especially in very low SNR conditions.
منابع مشابه
Integration of DNN based speech enhancement and ASR
Speech enhancement employing Deep Neural Networks (DNNs) is gaining strength as a data-driven alternative to classical Minimum Mean Square Error (MMSE) enhancement approaches. In the past, Observation Uncertainty approaches to integrate MMSE speech enhancement with Automatic Speech Recognition (ASR) have yielded good results as a lightweight alternative for robust ASR. In this paper we thus exp...
متن کاملUse of speech presence uncertainty with MMSE spectral energy estimation for robust automatic speech recognition
In this paper, we investigate the use of the minimum mean square error (MMSE) spectral energy estimator for use in environmentrobust automatic speech recognition (ASR). In the past, it has been common to use the MMSE log-spectral amplitude estimator for this task. However, this estimator was originally derived under subjective human listening criteria. Therefore its complex suppression rule may...
متن کاملOptimizing the Implementation of MMSE Enhancement for Robust Speech Recognition
In this paper several methods are proposed to optimize the implementation of minimum mean-square error (MMSE) estimation algorithm for robust automatic speech recognition (ASR). In the calculation of MMSE enhancement algorithm, the original confluent hyper-geometric function is approximated by a piece-wise linear function, which greatly reduces the computation load while keep the same performan...
متن کاملMask estimation in non-stationary noise environments for missing feature based robust speech recognition
In missing feature based automatic speech recognition (ASR), the role of the spectro-temporal mask in providing an accurate description of the relationship between target speech and environmental noise is critical for minimizing the degradation in ASR word accuracy (WAC) as the signal-to-noise ratio (SNR) decreases. This paper demonstrates the importance of accurate characterization of instanta...
متن کاملRobust automatic speech recognition using an optimal spectral amplitude estimator algorithm in low-SNR car environments
This paper addresses the problem of noise robustness of automatic speech recognition (ASR) systems in noisy car environments using a Minimum Mean-Square Error Short-Time Spectral Amplitude Estimator (MMSE-STSA). This was accomplished by the integration of an adaptive time varying Noise Shaping Filter (NSF) with the MMSE-STSA algorithm in order to improve the speech enhancement performance by “w...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2002